Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 14 hours
Course Outline
Module 1: Context, Scope, and Delivery Challenges
- Distinguishing between autocompletion and autonomous multi-step execution
- Addressing prevalent misconceptions regarding AI in software delivery
- Limitations of prompt optimization as a standalone solution
- Assessing participant tooling, operational pain points, and strategic objectives
- Selecting the appropriate AI operating model for engineering teams for government contexts
Module 2: Specification Ingestion and Structured Decomposition
- Developing a structural inventory of stakeholder documentation
- Techniques for extracting specific requirements
- Chunking methodologies: structural, semantic, and sliding-window approaches
- Maintaining integrity of dependencies and cross-references
- Handling complex inputs including tables, diagrams, flowcharts, and mixed media
- Effective management of context windows
Module 3: Boundaries of Human Judgment
- Identifying areas where human decision-making remains essential
- Recognizing hallucinated dependencies within AI outputs
- Detecting fabricated constraints and logical inversions
- Mitigating the risk of unsafe default behaviors
- Validation frameworks ensuring traceability, consistency, and completeness
Module 4: From Requirements to Code using Agentic Tools
- Adopting an architecture-first delivery model
- Mapping components and defining service boundaries
- Establishing API contracts as delivery anchors
- Implementing persistent rules and constraints within AI tools
- Linking task instructions directly to requirements
- Comparing minimal prompting versus constrained prompting approaches
- Contract-first generation for backend and frontend systems
Module 5: The Agentic Iteration Loop
- The self-correction cycle in agentic workflows
- Managing controlled iterative delivery cycles
- Reviewing diffs and code modifications
- Identifying scope creep and unauthorized changes
- Mitigating limitations in context memory
- Leveraging iteration history for continuous improvement
Module 6: Enforcing Code Quality
- Applying prompt constraints for edge case handling
- Using rules documents as dynamic governance artifacts
- Implementing automated gates via linting and static analysis
- Conducting security scans on AI-generated code
- Verifying dependency and architectural conformance
- Protocols for human review of AI outputs for government standards
Module 7: Feedback Loops and Continuous Improvement
- Integrating structured failures back into AI workflows
- Defining bounded iterations and termination criteria
- Logging cycles and recorded outcomes
- Evolving rules documents over time
- Building reusable engineering intelligence
Module 8: Security Anti-Patterns in AI Delivery
- Common security risks present in generated code
- Technology-specific security rule appendices
- Implementing pre-commit security scanning
- Secure SDLC controls for AI-assisted development
- Establishing human accountability in secure delivery processes
Module 9: Testing Aligned with Specifications
- Deriving test specifications from requirements
- Designing tests using domain language
- Safely generating test implementations
- Concepts in mutation testing
- Validating specification coverage
- Reviewing assertion strength
- Models for diagnostic questioning
Module 10: System Maintenance
- Maintaining living artifacts: contracts, maps, rules, and test specs
- Evolving constraints over time
- AI governance for long-term maintainability
- Preventing technical debt through AI controls
- Operating models for sustainable AI engineering teams for government
Requirements
Participants should possess the following qualifications:
- Experience in software development projects
- Understanding of application architecture fundamentals
- Familiarity with APIs, backend/frontend systems, or full-stack delivery
- Basic knowledge of Agile or iterative software delivery
- Awareness of software testing concepts
- Exposure to AI coding tools is beneficial but not required
- Recommended for mid-level to senior technical professionals
